Human-Centric Approaches for Agricultural Optimization: Predicting Crop Yield Using Stacked Artificial Neural Networks

Abstract

In recent years, the integration of IoT sensors with advanced machine learning techniques, particularly stacked artificial neural networks (ANNs), has revolutionized smart farming practices. This approach utilizes real-time environmental data collected by IoT sensors to predict crop yield, optimize resource utilization, and enhance agricultural productivity. By employing stacked ANNs, which combine multiple layers of neural networks for more accurate modeling, the system can process complex data inputs such as temperature, humidity, solar radiation, and soil moisture. The deep learning models provide highly accurate predictions that enable farmers to make informed decisions regarding crop management, climate control, and resource allocation. This research demonstrates how the combination of IoT sensors and stacked ANNs can significantly improve efficiency and sustainability in agriculture, paving the way for more data-driven, human-centric farming solutions.